8 papers
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
Xinyu Yuan, Xixian Liu, Jianan Zhao +3
Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved condition…
MatterSim-MT: A multi-task foundation model for in silico materials characterization
Han Yang, Xixian Liu, Chenxi Hu +25
Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progres…
GeneZip: Region-Aware Compression for Long Context DNA Modeling
Jianan Zhao, Xixian Liu, Zhihao Zhan +3
Long-context DNA models are limited by token-mixing cost and by how compression allocates representational budget across the genome. Existing approaches operate close to base-pair…
Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
Haocheng Tang, Liang Shi, Ya-Shi Zhang +3
Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics simulations and the scarcity of d…
PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
Xinyu Yuan, Xixian Liu, Ya Shi Zhang +3
Building Virtual Cells that can accurately simulate cellular responses to perturbations is a long-standing goal in systems biology. A fundamental challenge is that high-throughput…
Learning 3D Anisotropic Noise Distributions Improves Molecular Force Field Modeling
Xixian Liu, Rui Jiao, Zhiyuan Liu +6
Coordinate denoising has emerged as a promising method for 3D molecular pretraining due to its theoretical connection to learning molecular force field. However, existing denoising…